用于加密货币异常检测的无注意力条件自编码器
An Attention Free Conditional Autoencoder For Anomaly Detection in Cryptocurrencies
AI总结：
本文针对含噪加密货币时间序列异常检测，提出在条件自编码器中加入 Attention-Free LSTM 层的 AF-CA，相较 LSTM Autoencoder 提升了解释能力与异常检测效果。
摘要：
识别时间序列中的异常十分困难，尤其是在存在大量噪声时。去噪技术可以去除噪声，但该技术可能导致显著的信息损失。为检测时间序列中的异常，我们提出了一种无注意力条件自编码器（AF-CA）。我们从条件自编码器模型出发，在其上添加了一个 Attention-Free LSTM 层，以使异常检测能力更加可靠，并增强异常检测的能力。我们将所提出的 Attention Free Conditional Autoencoder 的结果与 LSTM Autoencoder 的结果进行了比较，结果表明该模型的解释能力得到了明显提升，从而也改善了含噪时间序列中的异常检测。
英文摘要：
It is difficult to identify anomalies in time series, especially when there is a lot of noise. Denoising techniques can remove the noise but this technique can cause a significant loss of information. To detect anomalies in the time series we have proposed an attention free conditional autoencoder (AF-CA). We started from the autoencoder conditional model on which we added an Attention-Free LSTM layer \cite{inzirillo2022attention} in order to make the anomaly detection capacity more reliable and to increase the power of anomaly detection. We compared the results of our Attention Free Conditional Autoencoder with those of an LSTM Autoencoder and clearly improved the explanatory power of the model and therefore the detection of anomaly in noisy time series.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
